© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 222331
    Prev
    Next
    INDEX
    Explanations

    users with

    np_acts-logits-general · gemini-2.5-flash-lite

    balance diversity stability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    editing
    0.50
     कपड़ों
    0.48
     थोड़ी
    0.47
    軖
    0.46
    fourths
    0.45
    eck
    0.45
    <0xAD>
    0.45
    oque
    0.45
    ellipsis
    0.45
    osts
    0.45
    POSITIVE LOGITS
     ameryka
    0.60
    '
    0.60
     ná
    0.57
     Ná
    0.56
     –
    0.55
     méridionale
    0.54
     it
    0.53
     American
    0.52
     America
    0.52
     ấy
    0.52
    Activations Density 0.000%

    No Known Activations